Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security vulnerabilities, particularly when these knowledge bases are publicly accessible and modifiable. While previous studies have exposed knowledge poisoning risks in RAG systems, existing attack methods suffer from critical limitations: they either require injecting multiple poisoned documents (resulting in poor stealthiness) or can only function effectively on simplistic queries (limiting real-world applicability). This paper reveals a more realistic knowledge poisoning attack against RAG systems that achieves successful attacks by poisoning only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements. Our proposed AuthChain address three challenges to ensure the poisoned documents are reliably retrieved and trusted by the LLM, even against large knowledge bases and LLM's own knowledge. Extensive experiments across six popular LLMs demonstrate that AuthChain achieves significantly higher attack success rates while maintaining superior stealthiness against RAG defense mechanisms compared to state-of-the-art baselines.

Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising and previously overlooked phenomenon: explicit CoT reasoning can significantly degrade instruction-following accuracy. Evaluating 15 models on two benchmarks: IFEval (with simple, rule-verifiable constraints) and ComplexBench (with complex, compositional constraints), we consistently observe performance drops when CoT prompting is applied. Through large-scale case studies and an attention-based analysis, we identify common patterns where reasoning either helps (e.g., with formatting or lexical precision) or hurts (e.g., by neglecting simple constraints or introducing unnecessary content). We propose a metric, constraint attention, to quantify model focus during generation and show that CoT reasoning often diverts attention away from instruction-relevant tokens. To mitigate these effects, we introduce and evaluate four strategies: in-context learning, self-reflection, self-selective reasoning, and classifier-selective reasoning. Our results demonstrate that selective reasoning strategies, particularly classifier-selective reasoning, can substantially recover lost performance. To our knowledge, this is the first work to systematically expose reasoning-induced failures in instruction-following and offer practical mitigation strategies.

Collaborative filtering (CF) enables large-scale recommendation systems by encoding information from historical user-item interactions into dense ID-embedding tables. However, as embedding tables grow, closed-form solutions become impractical, often necessitating the use of mini-batch gradient descent for training. Despite extensive work on designing loss functions to train CF models, we argue that one core component of these pipelines is heavily overlooked: weight decay. Attaining high-performing models typically requires careful tuning of weight decay, regardless of loss, yet its necessity is not well understood. In this work, we question why weight decay is crucial in CF pipelines and how it impacts training. Through theoretical and empirical analysis, we surprisingly uncover that weight decay's primary function is to encode popularity information into the magnitudes of the embedding vectors. Moreover, we find that tuning weight decay acts as a coarse, non-linear knob to influence preference towards popular or unpopular items. Based on these findings, we propose PRISM (Popularity-awaRe Initialization Strategy for embedding Magnitudes), a straightforward yet effective solution to simplify the training of high-performing CF models. PRISM pre-encodes the popularity information typically learned through weight decay, eliminating its necessity. Our experiments show that PRISM improves performance by up to 4.77% and reduces training times by 38.48%, compared to state-of-the-art training strategies. Additionally, we parameterize PRISM to modulate the initialization strength, offering a cost-effective and meaningful strategy to mitigate popularity bias.

Visual storytelling systems struggle to maintain character identity across frames and link actions to appropriate subjects, frequently leading to referential hallucinations. These issues can be addressed through grounding of characters, objects, and other entities on the visual elements. We propose StoryReasoning, a dataset containing 4,178 stories derived from 52,016 movie images, with both structured scene analyses and grounded stories. Each story maintains character and object consistency across frames while explicitly modeling multi-frame relationships through structured tabular representations. Our approach features cross-frame object re-identification using visual similarity and face recognition, chain-of-thought reasoning for explicit narrative modeling, and a grounding scheme that links textual elements to visual entities across multiple frames. We establish baseline performance by fine-tuning Qwen2.5-VL 7B, creating Qwen Storyteller, which performs end-to-end object detection, re-identification, and landmark detection while maintaining consistent object references throughout the story. Evaluation demonstrates a reduction from 4.06 to 3.56 (-12.3%) hallucinations on average per story and an improvement in creativity from 2.58 to 3.38 (+31.0%) when compared to a non-fine-tuned model.

One long-standing goal in robotics is to train a "generalist" robot capable of performing diverse tasks, particularly robot manipulation. A promising paradigm for this is to leverage the broad knowledge in Vision-Language Models (VLMs) such as GPT -4 [1] and Gemini [2]. While the community has used VLMs to achieve great generalization in domains like computer vision and natural language processing, robotics faces unique challenges with requiring either difficult-to-scale physical real-world interaction data or simulation data with sim-to-real gaps, making it challenging for VLMs to act as low-level planners. However, recent work has extensively explored incorporating these "foundation" models [3] such that they can generate low-level trajectories executable by an embodiment [4, 5, 6, 7]. This direction is especially important because it offers a path to bypass large-scale, task-specific data collection by leveraging general-purpose pre-trained models. Beyond improving scalability, this enables faster deployment in open-world settings where generalization to unseen tasks and objects is critical. It remains unclear, however, which is the optimal foundation model for a "VLM agent" in tasks like fabric or articulated object manipulation, and how VLMs perform in low-level reasoning tasks required for manipulation. Motivated from these questions, we propose ManipBench: a novel open-source benchmark to evaluate how well VLMs understand the low-level effect of a robot's action on its environment (see Figure 1). While there exist benchmarks to evaluate VLMs for robotics [8, 9, 10, 11, 12, 13, 14, 15, 16], our approach and benchmark differ significantly along axes such as task diversity, model diversity, and particularly our novel multiple-choice question (MCQ) based evaluation design, which efficiently assesses the low-level reasoning capabilities of VLMs without requiring trajectory rollouts, as detailed in Table 1.

Natural disasters, including earthquakes, wildfires and cyclones, bear a huge risk on human lives as well as infrastructure assets. An effective response to disaster depends on the ability to rapidly and efficiently assess the intensity of damage. Artificial Intelligence (AI) and Generative Artificial Intelligence (GenAI) presents a breakthrough solution, capable of combining knowledge from multiple types and sources of data, simulating realistic scenarios of disaster, and identifying emerging trends at a speed previously unimaginable. In this paper, we present a comprehensive review on the prospects of AI and GenAI in damage assessment for various natural disasters, highlighting both its strengths and limitations. We talk about its application to multimodal data such as text, image, video, and audio, and also cover major issues of data privacy, security, and ethical use of the technology during crises. The paper also recognizes the threat of Generative AI misuse, in the form of dissemination of misinformation and for adversarial attacks. Finally, we outline avenues of future research, emphasizing the need for secure, reliable, and ethical Generative AI systems for disaster management in general. We believe that this work represents the first comprehensive survey of Gen-AI techniques being used in the field of Disaster Assessment and Response.

Artificial Intelligence (AI) is rapidly expanding and integrating more into daily life to automate tasks, guide decision making, and enhance efficiency. However, complex AI models, which make decisions without providing clear explanations (known as the "black-box problem"), currently restrict trust and widespread adoption of AI. Explainable Artificial Intelligence (XAI) has emerged to address the black-box problem of making AI systems more interpretable and transparent so stakeholders can trust, verify, and act upon AI-based outcomes. Researchers have developed various techniques to foster XAI in the Software Development Lifecycle. However, there are gaps in applying XAI techniques in the Software Engineering phases. Literature review shows that 68% of XAI in Software Engineering research is focused on maintenance as opposed to 8% on software management and requirements. In this paper, we present a comprehensive survey of the applications of XAI methods such as concept-based explanations, Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), rule extraction, attention mechanisms, counterfactual explanations, and example-based explanations to the different phases of the Software Development Life Cycle (SDLC), including requirements elicitation, design and development, testing and deployment, and evolution. To the best of our knowledge, this paper presents the first comprehensive survey of XAI techniques for every phase of the Software Development Life Cycle (SDLC). This survey aims to promote explainable AI in Software Engineering and facilitate the practical application of complex AI models in AI-driven software development.

Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving partial differential equations (PDEs) by embedding physical laws directly into the loss function. However, as a fundamental optimization issue, internal covariate shift (ICS) hinders the stable and effective training of PINNs by disrupting feature distributions and limiting model expressiveness. Unlike standard deep learning tasks, conventional remedies for ICS -- such as Batch Normalization and Layer Normalization -- are not directly applicable to PINNs, as they distort the physical consistency required for reliable PDE solutions. To address this issue, we propose Mask-PINNs, a novel architecture that introduces a learnable mask function to regulate feature distributions while preserving the underlying physical constraints of PINNs. We provide a theoretical analysis showing that the mask suppresses the expansion of feature representations through a carefully designed modulation mechanism. Empirically, we validate the method on multiple PDE benchmarks -- including convection, wave propagation, and Helmholtz equations -- across diverse activation functions. Our results show consistent improvements in prediction accuracy, convergence stability, and robustness. Furthermore, we demonstrate that Mask-PINNs enable the effective use of wider networks, overcoming a key limitation in existing PINN frameworks.

Sparse observations and coarse-resolution climate models limit effective regional decision-making, underscoring the need for robust downscaling. However, existing AI methods struggle with generalization across variables and geographies and are constrained by the quadratic complexity of Vision Transformer (ViT) self-attention. We introduce ORBIT-2, a scalable foundation model for global, hyper-resolution climate downscaling. ORBIT-2 incorporates two key innovations: (1) Residual Slim ViT (Reslim), a lightweight architecture with residual learning and Bayesian regularization for efficient, robust prediction; and (2) TILES, a tile-wise sequence scaling algorithm that reduces self-attention complexity from quadratic to linear, enabling long-sequence processing and massive parallelism. ORBIT-2 scales to 10 billion parameters across 65,536 GPUs, achieving up to 4.1 exaFLOPS sustained throughput and 74--98% strong scaling efficiency. It supports downscaling to 0.9 km global resolution and processes sequences up to 4.2 billion tokens. On 7 km resolution benchmarks, ORBIT-2 achieves high accuracy with $R^2$ scores in the range of 0.98--0.99 against observational data.

Future robotic systems operating in real-world environments will require on-board embodied intelligence without continuous cloud connection, balancing capabilities with constraints on computational power and memory. This work presents an extension of the R1-zero approach, which enables the usage of low parameter-count Large Language Models (LLMs) in the robotic domain. The R1-Zero approach was originally developed to enable mathematical reasoning in LLMs using static datasets. We extend it to the robotics domain through integration in a closed-loop Reinforcement Learning (RL) framework. This extension enhances reasoning in Embodied Artificial Intelligence (Embodied AI) settings without relying solely on distillation of large models through Supervised Fine-Tuning (SFT). We show that small-scale LLMs can achieve effective reasoning performance by learning through closed-loop interaction with their environment, which enables tasks that previously required significantly larger models. In an autonomous driving setting, a performance gain of 20.2%-points over the SFT-based baseline is observed with a Qwen2.5-1.5B model. Using the proposed training procedure, Qwen2.5-3B achieves a 63.3% control adaptability score, surpassing the 58.5% obtained by the much larger, cloud-bound GPT-4o. These results highlight that practical, on-board deployment of small LLMs is not only feasible but can outperform larger models if trained through environmental feedback, underscoring the importance of an interactive learning framework for robotic Embodied AI, one grounded in practical experience rather than static supervision.